INDEX

Explanations

references to local entities or concepts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rape

-0.16

å¹ķ

-0.15

epy

-0.15

ARY

-0.14

ippet

-0.14

emit

-0.14

anye

-0.14

ç´ł

-0.14

mary

-0.13

acente

-0.13

POSITIVE LOGITS

ised

0.32

izing

0.26

isation

0.26

vore

0.24

ized

0.24

/global

0.24

ities

0.23

-global

0.23

izable

0.23

izations

0.22

Activations Density 0.029%

references to local entities or concepts

No Comments

No Known Activations